How many data sets does it take to accurately train a surrogate model?
2024/08/19
The answer can be found in the latest publication of our PostDoc Maximilian Kannapinn – it's just two!
Simulation-based digital twins represent an effort to provide high-accuracy real-time insights into operational physical processes. However, the computation time of many multi-physical simulation models is far from real-time. It might even exceed sensible time frames to produce sufficient data for training data-driven reduced-order models. This study presents TwinLab, a framework for data-efficient, yet accurate training of neural-ODE type reduced-order models with only two data sets.
For more insights, have a look at the publication “TwinLab: a framework for data-efficient training of non-intrusive reduced-order models for digital twins”. The paper is published in the ECCOMAS CM4P conference’s special issue: https://doi.org/10.1108/EC-11-2023-0855
You can also check out the preprint on arXiv: https://arxiv.org/abs/2407.03924